SatishBethi's picture
First Model
525be54
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5572478175163269,
"min": 0.5386313199996948,
"max": 1.3910027742385864,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16574.779296875,
"min": 16167.55859375,
"max": 42197.4609375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989962.0,
"min": 29952.0,
"max": 989962.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989962.0,
"min": 29952.0,
"max": 989962.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.19189460575580597,
"min": -0.09870325028896332,
"max": 0.20162059366703033,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 48.74123001098633,
"min": -23.688779830932617,
"max": 51.211631774902344,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.0066856518387794495,
"min": -0.013917215168476105,
"max": 0.5439726114273071,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -1.6981555223464966,
"min": -3.534972667694092,
"max": 128.9215087890625,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06850204886589696,
"min": 0.06507357036092752,
"max": 0.07289688525077552,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9590286841225574,
"min": 0.48399625766631643,
"max": 1.0372182905557565,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.008899715815304382,
"min": 0.0001361964184250879,
"max": 0.011019201556337064,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.12459602141426135,
"min": 0.0019067498579512304,
"max": 0.1542688217887189,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.659804589621429e-06,
"min": 7.659804589621429e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010723726425470001,
"min": 0.00010723726425470001,
"max": 0.0036333232888923,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10255323571428573,
"min": 0.10255323571428573,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4357453000000002,
"min": 1.3886848,
"max": 2.6111077,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002650682478571429,
"min": 0.0002650682478571429,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00371095547,
"min": 0.00371095547,
"max": 0.12112965923,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01410889346152544,
"min": 0.01410889346152544,
"max": 0.3948425352573395,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19752450287342072,
"min": 0.19752450287342072,
"max": 2.763897657394409,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 648.3125,
"min": 607.3877551020408,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31119.0,
"min": 15984.0,
"max": 32298.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.8932458052101234,
"min": -1.0000000521540642,
"max": 0.8932458052101234,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 42.875798650085926,
"min": -31.989601641893387,
"max": 42.875798650085926,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.8932458052101234,
"min": -1.0000000521540642,
"max": 0.8932458052101234,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 42.875798650085926,
"min": -31.989601641893387,
"max": 42.875798650085926,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.09404990300269371,
"min": 0.09404990300269371,
"max": 7.611463585868478,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.514395344129298,
"min": 4.514395344129298,
"max": 121.78341737389565,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674758248",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674760350"
},
"total": 2102.716744429,
"count": 1,
"self": 0.5249121119995834,
"children": {
"run_training.setup": {
"total": 0.11594565199993667,
"count": 1,
"self": 0.11594565199993667
},
"TrainerController.start_learning": {
"total": 2102.0758866650003,
"count": 1,
"self": 1.7838245098801053,
"children": {
"TrainerController._reset_env": {
"total": 6.298491405999812,
"count": 1,
"self": 6.298491405999812
},
"TrainerController.advance": {
"total": 2093.905993407121,
"count": 63299,
"self": 1.7025431923084398,
"children": {
"env_step": {
"total": 1407.0521682800663,
"count": 63299,
"self": 1277.6079131370125,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.3829707910054,
"count": 63299,
"self": 5.115100918948883,
"children": {
"TorchPolicy.evaluate": {
"total": 123.26786987205651,
"count": 62573,
"self": 41.0107970351246,
"children": {
"TorchPolicy.sample_actions": {
"total": 82.25707283693191,
"count": 62573,
"self": 82.25707283693191
}
}
}
}
},
"workers": {
"total": 1.0612843520484603,
"count": 63299,
"self": 0.0,
"children": {
"worker_root": {
"total": 2095.8348141662673,
"count": 63299,
"is_parallel": true,
"self": 941.1229038961274,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018078029997923295,
"count": 1,
"is_parallel": true,
"self": 0.000664938998852449,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011428640009398805,
"count": 8,
"is_parallel": true,
"self": 0.0011428640009398805
}
}
},
"UnityEnvironment.step": {
"total": 0.04912068699923111,
"count": 1,
"is_parallel": true,
"self": 0.0005038569979660679,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005007650006518816,
"count": 1,
"is_parallel": true,
"self": 0.0005007650006518816
},
"communicator.exchange": {
"total": 0.046332585000527615,
"count": 1,
"is_parallel": true,
"self": 0.046332585000527615
},
"steps_from_proto": {
"total": 0.0017834800000855466,
"count": 1,
"is_parallel": true,
"self": 0.00046568000016122824,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013177999999243184,
"count": 8,
"is_parallel": true,
"self": 0.0013177999999243184
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1154.71191027014,
"count": 63298,
"is_parallel": true,
"self": 30.957620933185353,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.639935032986614,
"count": 63298,
"is_parallel": true,
"self": 25.639935032986614
},
"communicator.exchange": {
"total": 986.0553037659283,
"count": 63298,
"is_parallel": true,
"self": 986.0553037659283
},
"steps_from_proto": {
"total": 112.05905053803963,
"count": 63298,
"is_parallel": true,
"self": 27.4860797560259,
"children": {
"_process_rank_one_or_two_observation": {
"total": 84.57297078201373,
"count": 506384,
"is_parallel": true,
"self": 84.57297078201373
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 685.1512819347463,
"count": 63299,
"self": 3.1412648536970664,
"children": {
"process_trajectory": {
"total": 155.23856988605985,
"count": 63299,
"self": 155.04465968505974,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19391020100010792,
"count": 2,
"self": 0.19391020100010792
}
}
},
"_update_policy": {
"total": 526.7714471949894,
"count": 451,
"self": 201.44817089387652,
"children": {
"TorchPPOOptimizer.update": {
"total": 325.32327630111286,
"count": 22794,
"self": 325.32327630111286
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.529994713375345e-07,
"count": 1,
"self": 9.529994713375345e-07
},
"TrainerController._save_models": {
"total": 0.08757638899987796,
"count": 1,
"self": 0.001447713999368716,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08612867500050925,
"count": 1,
"self": 0.08612867500050925
}
}
}
}
}
}
}